Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 2721 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1312. Min Range: -0.1312

Max Act: 0.1312. Min Act: -0.0001

Data Index: 1479629 (Python Code)

Max Activating Token Index: 613

Text #1

Max Range: 0.1312. Min Range: -0.1312

Max Act: 0.1277. Min Act: -0.0001

Data Index: 1416354 (Python Code)

Max Activating Token Index: 51

Text #2

Max Range: 0.1312. Min Range: -0.1312

Max Act: 0.1240. Min Act: -0.0001

Data Index: 1584346 (Python Code)

Max Activating Token Index: 390

Text #3

Max Range: 0.1312. Min Range: -0.1312

Max Act: 0.1221. Min Act: -0.0001

Data Index: 1369135 (Python Code)

Max Activating Token Index: 113

Text #4

Max Range: 0.1312. Min Range: -0.1312

Max Act: 0.1305. Min Act: -0.0001

Data Index: 1568177 (Python Code)

Max Activating Token Index: 922

Text #5

Max Range: 0.1312. Min Range: -0.1312

Max Act: 0.1242. Min Act: -0.0001

Data Index: 1577600 (Python Code)

Max Activating Token Index: 84

Text #6

Max Range: 0.1312. Min Range: -0.1312

Max Act: 0.1282. Min Act: -0.0001

Data Index: 1519021 (Python Code)

Max Activating Token Index: 258

Text #7

Max Range: 0.1312. Min Range: -0.1312

Max Act: 0.1141. Min Act: -0.0001

Data Index: 1553729 (Python Code)

Max Activating Token Index: 593

Text #8

Max Range: 0.1312. Min Range: -0.1312

Max Act: 0.1217. Min Act: -0.0001

Data Index: 1407892 (Python Code)

Max Activating Token Index: 113

Text #9

Max Range: 0.1312. Min Range: -0.1312

Max Act: 0.1201. Min Act: -0.0001

Data Index: 1641614 (Python Code)

Max Activating Token Index: 295

Text #10

Max Range: 0.1312. Min Range: -0.1312

Max Act: 0.1146. Min Act: -0.0001

Data Index: 1649954 (Python Code)

Max Activating Token Index: 351

Text #11

Max Range: 0.1312. Min Range: -0.1312

Max Act: 0.1200. Min Act: -0.0001

Data Index: 1492578 (Python Code)

Max Activating Token Index: 739

Text #12

Max Range: 0.1312. Min Range: -0.1312

Max Act: 0.1200. Min Act: -0.0001

Data Index: 1409146 (Python Code)

Max Activating Token Index: 55

Text #13

Max Range: 0.1312. Min Range: -0.1312

Max Act: 0.1194. Min Act: -0.0001

Data Index: 1370496 (Python Code)

Max Activating Token Index: 301

Text #14

Max Range: 0.1312. Min Range: -0.1312

Max Act: 0.1143. Min Act: -0.0001

Data Index: 1568017 (Python Code)

Max Activating Token Index: 328

Text #15

Max Range: 0.1312. Min Range: -0.1312

Max Act: 0.1183. Min Act: -0.0001

Data Index: 1598372 (Python Code)

Max Activating Token Index: 174

Text #16

Max Range: 0.1312. Min Range: -0.1312

Max Act: 0.1142. Min Act: -0.0001

Data Index: 1617973 (Python Code)

Max Activating Token Index: 391

Text #17

Max Range: 0.1312. Min Range: -0.1312

Max Act: 0.1145. Min Act: -0.0001

Data Index: 1419311 (Python Code)

Max Activating Token Index: 361

Text #18

Max Range: 0.1312. Min Range: -0.1312

Max Act: 0.1151. Min Act: -0.0001

Data Index: 1602129 (Python Code)

Max Activating Token Index: 849

Text #19

Max Range: 0.1312. Min Range: -0.1312

Max Act: 0.1186. Min Act: -0.0001

Data Index: 1372426 (Python Code)

Max Activating Token Index: 409